def start_getweiboinfo(self, response):
mainpageurl = 'http://weibo.com/u/' + str(
self.uid) + '?from=otherprofile&wvr=3.6&loc=tagweibo&is_all=1&'
GetWeibopage.data['uid'] = self.uid
getweibopage = GetWeibopage()
for page in range(int(self.per_page_num), int(self.per_page_num) + 2):
GetWeibopage.data['page'] = page
firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
yield Request(url=firstloadurl,
meta={
'cookiejar': response.meta['cookiejar'],
'uid': self.uid
},
callback=self.parse_load)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl()
yield Request(url=secondloadurl,
meta={
'cookiejar': response.meta['cookiejar'],
'uid': self.uid
},
callback=self.parse_load)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,
meta={
'cookiejar': response.meta['cookiejar'],
'uid': self.uid
},
callback=self.parse_load)
def start_getweiboinfo(self,response):
# db = OracleStore()
# conn = db.get_connection()
# sql1 = '''select * from "t_user_keyword" where "keyword" = '%s' ''' % str((self.keyword))
# cursor1 = db.select_operation(conn,sql1)
#
# sql2 = '''select count(*) from "t_user_keyword" where "keyword" = '%s' ''' % str((self.keyword))
# cursor2 = db.select_operation(conn,sql2)
# count = cursor2.fetchone()
#
# if count[0]:
# for i in range(1): #(count[0]):
# for result in cursor1.fetchmany(1):
# if result[0]:
mainpageurl = 'http://weibo.com/u/'+str(self.uid)+'?from=otherprofile&wvr=3.6&loc=tagweibo&is_all=1&'
GetWeibopage.data['uid'] = self.uid #result[0]
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page+1
firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
yield Request(url=firstloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':self.uid},callback=self.parse_load)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl()
yield Request(url=secondloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':self.uid},callback=self.parse_load)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':self.uid},callback=self.parse_load)
def parse_total_page(self, response):
analyzer = Analyzer()
total_pq = analyzer.get_html(response.body,
'script:contains("W_pages")')
friendcircle_analyzer = keyword_info_analyzer()
total_pages = friendcircle_analyzer.get_totalpages(
total_pq) #需要爬取的微博朋友圈页数
logger.info("the total_pages is: %d", total_pages)
getweibopage = GetWeibopage()
mainpage_url = response.meta['mainpage_url']
user_id = response.meta['uid']
is_search = response.meta['is_search']
for page in range(1): #TODO 此处要更改为total_pages
GetWeibopage.data['uid'] = user_id
GetWeibopage.data['page'] = page + 1
firstload_url = mainpage_url + getweibopage.get_firstloadurl()
yield Request(url=firstload_url,
meta={
'cookiejar': response.meta['cookiejar'],
'uid': user_id,
'is_search': is_search
},
callback=self.parse_load)
secondload_url = mainpage_url + getweibopage.get_secondloadurl()
#yield Request(url=secondload_url,meta={'cookiejar':response.meta['cookiejar'],'uid':user_id,'is_search':is_search},callback=self.parse_load)
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
def start_getweiboinfo(self,response):
db = MysqlStore()
conn = db.get_connection()
sql1 = "select * from t_user_follow where contentstate = 0"
cursor1 = db.select_operation(conn,sql1)
sql2 = "select count(*) from t_user_follow where contentstate = 0"
cursor2 = db.select_operation(conn,sql2)
count = cursor2.fetchone()
for i in range(10): #(count[0]): #count[0]为需要再爬取的用户数
for result in cursor1.fetchmany(1):
if result[1]:
mainpageurl = 'http://weibo.com/u/'+str(result[1])+'?from=otherprofile&wvr=3.6&loc=tagweibo'
GetWeibopage.data['uid'] = result[1]
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page+1
firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
yield Request(url=firstloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':result[1]},callback=self.parse_firstload)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl()
yield Request(url=secondloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':result[1]},callback=self.parse_secondload)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':result[1]},callback=self.parse_thirdload)
def start_getweiboinfo(self,response):
db = OracleStore();conn = db.get_connection()
sql1 = '''select * from t_user_info'''
cursor1 = db.select_operation(conn,sql1)
sql2 = '''select count(*) from t_user_info'''
cursor2 = db.select_operation(conn,sql2)
count = cursor2.fetchone()
if count[0]:
for i in range(count[0]):
for result in cursor1.fetchmany(1):
mainpageurl = 'http://weibo.com/u/'+str(result[0])+'?from=otherprofile&wvr=3.6&loc=tagweibo'
GetWeibopage.data['uid'] = result[0]
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page+1
firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
yield Request(url=firstloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':result[0]},callback=self.parse_load)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl()
yield Request(url=secondloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':result[0]},callback=self.parse_load)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':result[0]},callback=self.parse_load)
else:
yield None
db.close_connection(conn,cursor1,cursor2)
def get_userinfo(self,response):
mainpageurl = 'http://weibo.com/u/'+str(1227086635)+'?from=otherprofile&wvr=3.6&loc=tagweibo'
GetWeibopage.data['uid'] = 1227086635
getweibopage = GetWeibopage()
GetWeibopage.data['page'] = 1
#firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar']},callback=self.get_userurl)
def start_getweibo_info(self,response):
db = MysqlStore();
#取出没有爬取过的且is_delete=0的重点人员
GetWeibopage.data['page'] = 1; getweibopage = GetWeibopage()
for round in range(1): #遍历数据库的轮数
conn = db.get_connection()
sql1 = "select user_id from cauc_black_man_test a \
where a.is_search = 0 and a.is_delete = 0"
cursor = db.select_operation(conn,sql1)
for user_id in cursor.fetchall():
user_id = user_id[0]
logger.info("this is the unsearched user_id:%s",user_id)
#更新is_search标志位为1
sql2 = "update cauc_black_man_test set is_search = 1 where user_id = '%s'" % user_id
db.update_operation(conn,sql2)
#获取需要爬取的总页面数
start_time = self.start_time;end_time = get_current_time('hour')
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
yield Request(url=thirdload_url,meta={'cookiejar':response.meta['cookiejar'],'mainpage_url':mainpage_url,'uid':user_id,'is_search':0},callback=self.parse_total_page)
logger.info("current timestamp:%d",int(time.time()))
#设置循环爬取间隔
time.sleep(WeiboSpider.settings['FRIENDCIRCAL_INTERVAL']) #可以采用间隔15min
#取出已经爬取过is_search=1的且is_delete=0的重点人员
sql3 = "select user_id from cauc_black_man_test a \
where a.is_search = 1 and a.is_delete = 0"
cursor = db.select_operation(conn,sql3)
for user_id in cursor.fetchall():
user_id = user_id[0]
logger.info("this is the searched user_id:%s",user_id)
start_time = get_time_by_interval(int(time.time()),86400,'hour');end_time = get_current_time('hour') #起始和结束间隔时间为1天(86400s)
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
#yield Request(url=thirdload_url,meta={'cookiejar':response.meta['cookiejar'],'mainpage_url':mainpage_url,'uid':user_id,'is_search':1},callback=self.parse_total_page)
conn.close()
def start_getweibo_info(self,response):
db = MysqlStore();
#取出没有爬取过的且is_delete=0的重点人员
GetWeibopage.data['page'] = 1; getweibopage = GetWeibopage()
for round in range(1): #遍历数据库的轮数
conn = db.get_connection()
sql1 = "select user_id from cauc_warning_man_test a \
where a.is_search = 0 and a.is_delete = 0"
cursor = db.select_operation(conn,sql1)
for user_id in cursor.fetchall():
user_id = user_id[0]
logger.info("this is the unsearched user_id:%s",user_id)
#更新is_search标志位为1
sql2 = "update cauc_warning_man_test set is_search = 1 where user_id = '%s'" % user_id
db.update_operation(conn,sql2)
#获取需要爬取的总页面数
start_time = self.start_time;end_time = get_current_time('hour')
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
yield Request(url=thirdload_url,meta={'cookiejar':response.meta['cookiejar'],'mainpage_url':mainpage_url,'uid':user_id,'is_search':0},callback=self.parse_total_page)
logger.info("current timestamp:%d",int(time.time()))
#设置循环爬取间隔
time.sleep(WeiboSpider.settings['WEIBOCONTENT_INTERVAL']) #可以采用间隔15min
#取出已经爬取过is_search=1的且is_delete=0的预警人员
sql3 = "select user_id from cauc_warning_man_test a \
where a.is_search = 1 and a.is_delete = 0"
cursor = db.select_operation(conn,sql3)
for user_id in cursor.fetchall():
user_id = user_id[0]
logger.info("this is the searched user_id:%s",user_id)
start_time = get_time_by_interval(int(time.time()),86400,'hour');end_time = get_current_time('hour') #起始和结束间隔时间为1天(86400s)
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
#yield Request(url=thirdload_url,meta={'cookiejar':response.meta['cookiejar'],'mainpage_url':mainpage_url,'uid':user_id,'is_search':1},callback=self.parse_total_page)
conn.close()
def start_getweibo_info(self,response):
db = MysqlStore();
#取出没有爬取过的且is_delete=0的重点人员
GetWeibopage.data['page'] = 1; getweibopage = GetWeibopage()
#for round in range(1): #遍历数据库的轮数
conn = db.get_connection()
sql1 = "select user_id from cauc_warning_man a \
where a.is_search = 0 and a.is_delete = 0"
cursor1 = db.select_operation(conn,sql1)
for user_id in cursor1.fetchall():
user_id = user_id[0]
logger.info("this is the unsearched user_id:%s",user_id)
#获取需要爬取的总页面数
start_time = self.start_time;end_time = get_current_time('day')
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
yield Request(url=thirdload_url,cookies=random.choice(COOKIES),meta={'mainpage_url':mainpage_url,'uid':user_id,'is_search':0},callback=self.parse_total_page)
#取出已经爬取过is_search=1的且is_delete=0的预警人员
sql2 = "select user_id from cauc_warning_man a \
where a.is_search = 1 and a.is_delete = 0"
cursor2 = db.select_operation(conn,sql2)
for user_id in cursor2.fetchall():
user_id = user_id[0]
logger.info("this is the searched user_id:%s",user_id)
#start_time = get_time_by_interval(int(time.time()),86400,'day');end_time = get_current_time('day') #起始和结束间隔时间为1天(86400s),即过去一天的内容
start_time = get_time_by_interval(int(time.time()),int(self.interval),'day');end_time = get_current_time('day') #起始和结束间隔时间为x天(由interval代表的秒换算而来)
mainpage_url = "http://weibo.com/" + str(user_id) + "?is_ori=1&is_forward=1&is_text=1&is_pic=1&key_word=&start_time=" + start_time + "&end_time=" + end_time + "&is_search=1&is_searchadv=1&"
GetWeibopage.data['uid'] = user_id;
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
yield Request(url=thirdload_url,cookies=random.choice(COOKIES),meta={'mainpage_url':mainpage_url,'uid':user_id,'is_search':1},callback=self.parse_total_page)
#更新is_search标志位为1
sql3 = "update cauc_warning_man set is_search = 1 where is_search = 0 and is_delete = 0"
db.update_operation(conn,sql3)
db.close_connection(conn)
def start_getweiboinfo(self, response):
db = OracleStore()
conn = db.get_connection()
sql1 = '''select * from t_user_info'''
cursor1 = db.select_operation(conn, sql1)
sql2 = '''select count(*) from t_user_info'''
cursor2 = db.select_operation(conn, sql2)
count = cursor2.fetchone()
if count[0]:
for i in range(count[0]):
for result in cursor1.fetchmany(1):
mainpageurl = 'http://weibo.com/u/' + str(
result[0]) + '?from=otherprofile&wvr=3.6&loc=tagweibo'
GetWeibopage.data['uid'] = result[0]
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page + 1
firstloadurl = mainpageurl + getweibopage.get_firstloadurl(
)
yield Request(url=firstloadurl,
meta={
'cookiejar':
response.meta['cookiejar'],
'uid': result[0]
},
callback=self.parse_load)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl(
)
yield Request(url=secondloadurl,
meta={
'cookiejar':
response.meta['cookiejar'],
'uid': result[0]
},
callback=self.parse_load)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl(
)
yield Request(url=thirdloadurl,
meta={
'cookiejar':
response.meta['cookiejar'],
'uid': result[0]
},
callback=self.parse_load)
else:
yield None
db.close_connection(conn, cursor1, cursor2)
def start_getweiboinfo(self,response):
mainpageurl = 'http://weibo.com/u/'+str(self.uid)+'?from=otherprofile&wvr=3.6&loc=tagweibo&is_all=1&'
GetWeibopage.data['uid'] = self.uid
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page+1
firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
yield Request(url=firstloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':self.uid},callback=self.parse_load)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl()
yield Request(url=secondloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':self.uid},callback=self.parse_load)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar'],'uid':self.uid},callback=self.parse_load)
def parse_userinfo(self,response):
item = response.meta['item']
#f=open('./text2.html','w')
#f.write(response.body)
analyzer = Analyzer()
total_pq = analyzer.get_html(response.body,'script:contains("PCD_text_b")')
#userinfo_dict = analyzer.get_userinfo(total_pq)
item['userinfo'] = analyzer.get_userinfo(total_pq)
#uid = item['uid']
mainpageurl = 'http://weibo.com/u/'+str(response.meta['uid'])+'?from=otherprofile&wvr=3.6&loc=tagweibo'
GetWeibopage.data['uid'] = response.meta['uid'] #uid
getweibopage = GetWeibopage()
GetWeibopage.data['page'] = WeiboSpider.page_num-1
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar'],'item':item,'uid':response.meta['uid'],'followlist':response.meta['followlist']},callback=self.parse_thirdload)
def parse_follow(self,response):
#print '************************ source request url:',response.request.url
item = WeibospiderItem()
analyzer = Analyzer()
total_pq = analyzer.get_followhtml(response.body)
#item['followuidlist'] = analyzer.get_follow(total_pq)
followlist = analyzer.get_follow(total_pq)
#item['userinfo'] = {}
oldflag,stopflag= getinfo.get_followflag(WeiboSpider.filename)
p = re.compile('.*_page=(\d).*',re.S)
current_page = p.search(response.request.url).group(1) #获取当前关注用户列表页页数
if int(current_page) == 1:
getinfo.set_followflag(WeiboSpider.filename,followlist[0],'False')
print 'page is equal 1 '
else:
print 'page is NOT equal 1'
for follow_uid in followlist[:2]:
print '%%%%%%%%%%%%%%%%%%%%%%%%%%',follow_uid
#item['uid'] = follow_uid
if follow_uid != oldflag: #对于已爬uid不进行重复爬取，即增量爬取
#爬取该uid用户主页微博内容
if stopflag == 'False':
getinfo.set_followflag(WeiboSpider.filename,followlist[0],'True')
mainpageurl = 'http://weibo.com/u/'+str(follow_uid)+'?from=otherprofile&wvr=3.6&loc=tagweibo'
GetWeibopage.data['uid'] = follow_uid
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page+1
#当页第一次加载
#当页第二次加载
#当页第三次加载
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
if int(GetWeibopage.data['pagebar']) == 1 and page == WeiboSpider.page_num-1: #在最后一页最后一次加载时，获取用户基本信息
print 'hhhhhhhhhhhhhhhhhhhh',followlist
yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar'],'item':item,'uid':follow_uid,'followlist':followlist},callback=self.get_userurl)
#continue
#yield Request(url=thirdloadurl,meta={'cookiejar':response.meta['cookiejar'],'item':item,'uid':follow_uid},callback=self.parse_thirdload)
#firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
#yield Request(url=firstloadurl,meta={'cookiejar':response.meta['cookiejar'],'item':item,'uid':follow_uid},callback=self.parse_firstload)
else:
break
else:
break
def start_getweiboinfo(self, response):
db = MysqlStore()
conn = db.get_connection()
sql1 = "select * from t_user_follow where contentstate = 0"
cursor1 = db.select_operation(conn, sql1)
sql2 = "select count(*) from t_user_follow where contentstate = 0"
cursor2 = db.select_operation(conn, sql2)
count = cursor2.fetchone()
for i in (count[0]): #count[0]为需要再爬取的用户数
for result in cursor1.fetchmany(1):
if result[1]:
mainpageurl = 'http://weibo.com/u/' + str(
result[1]) + '?from=otherprofile&wvr=3.6&loc=tagweibo'
GetWeibopage.data['uid'] = result[1]
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page + 1
firstloadurl = mainpageurl + getweibopage.get_firstloadurl(
)
yield Request(url=firstloadurl,
meta={
'cookiejar':
response.meta['cookiejar'],
'uid': result[1]
},
callback=self.parse_firstload)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl(
)
yield Request(url=secondloadurl,
meta={
'cookiejar':
response.meta['cookiejar'],
'uid': result[1]
},
callback=self.parse_secondload)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl(
)
yield Request(url=thirdloadurl,
meta={
'cookiejar':
response.meta['cookiejar'],
'uid': result[1]
},
callback=self.parse_thirdload)
def start_getweiboinfo(self, response):
# db = OracleStore()
# conn = db.get_connection()
# sql1 = '''select * from "t_user_keyword" where "keyword" = '%s' ''' % str((self.keyword))
# cursor1 = db.select_operation(conn,sql1)
#
# sql2 = '''select count(*) from "t_user_keyword" where "keyword" = '%s' ''' % str((self.keyword))
# cursor2 = db.select_operation(conn,sql2)
# count = cursor2.fetchone()
#
# if count[0]:
# for i in range(1): #(count[0]):
# for result in cursor1.fetchmany(1):
# if result[0]:
mainpageurl = 'http://weibo.com/u/' + str(
self.uid) + '?from=otherprofile&wvr=3.6&loc=tagweibo&is_all=1&'
GetWeibopage.data['uid'] = self.uid #result[0]
getweibopage = GetWeibopage()
for page in range(WeiboSpider.page_num):
GetWeibopage.data['page'] = page + 1
firstloadurl = mainpageurl + getweibopage.get_firstloadurl()
yield Request(url=firstloadurl,
meta={
'cookiejar': response.meta['cookiejar'],
'uid': self.uid
},
callback=self.parse_load)
secondloadurl = mainpageurl + getweibopage.get_secondloadurl()
yield Request(url=secondloadurl,
meta={
'cookiejar': response.meta['cookiejar'],
'uid': self.uid
},
callback=self.parse_load)
thirdloadurl = mainpageurl + getweibopage.get_thirdloadurl()
yield Request(url=thirdloadurl,
meta={
'cookiejar': response.meta['cookiejar'],
'uid': self.uid
},
callback=self.parse_load)
def parse_total_page(self,response):
analyzer = Analyzer()
total_pq = analyzer.get_html(response.body,'script:contains("W_pages")')
friendcircle_analyzer = keyword_info_analyzer()
total_pages = friendcircle_analyzer.get_totalpages(total_pq) #需要爬取的微博朋友圈页数
logger.info("the total_pages is: %d",total_pages)
getweibopage = GetWeibopage()
mainpage_url = response.meta['mainpage_url']
user_id = response.meta['uid']
is_search = response.meta['is_search']
for page in range(1): #TODO 此处要更改为total_pages
GetWeibopage.data['uid'] = user_id
GetWeibopage.data['page'] = page + 1
firstload_url = mainpage_url + getweibopage.get_firstloadurl()
yield Request(url=firstload_url,meta={'cookiejar':response.meta['cookiejar'],'uid':user_id,'is_search':is_search},callback=self.parse_load)
secondload_url = mainpage_url + getweibopage.get_secondloadurl()
#yield Request(url=secondload_url,meta={'cookiejar':response.meta['cookiejar'],'uid':user_id,'is_search':is_search},callback=self.parse_load)
thirdload_url = mainpage_url + getweibopage.get_thirdloadurl()
